© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30891
    Prev
    Next
    INDEX
    Explanations

    notice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imprisonment
    -0.08
    ासाठी
    -0.08
     تحمل
    -0.08
    ၀
    -0.08
    ними
    -0.08
     임
    -0.07
    ั
    -0.07
     Excav
    -0.07
     Roller
    -0.07
    useum
    -0.07
    POSITIVE LOGITS
     noticing
    0.10
     noticed
    0.09
    েলা
    0.09
    察
    0.09
    Patterns
    0.08
     deter
    0.08
     NOTICE
    0.08
     patterns
    0.08
    别人
    0.08
     needle
    0.08
    Activations Density 0.028%

    No Known Activations